Data Mining Practical Machine Learning Tools and Techniques

In the last decades, 3D city models appear to have been predominantly used for visualisation; however, today they are being increasingly employed in a number of domains and for a large range of tasks beyond visualisation. In this paper, we seek to understand and document the state of the art regarding the utilisation of 3D city models across multiple domains based on a comprehensive literature study including hundreds of research papers, technical reports and online resources. A challenge in a study such as ours is that the ways in which 3D city models are used cannot be readily listed due to fuzziness, terminological ambiguity, unclear added-value of 3D geoinformation in some instances, and absence of technical information. To address this challenge, we delineate a hierarchical terminology (spatial operations, use cases, applications), and develop a theoretical reasoning to segment and categorise the diverse uses of 3D city models. Following this framework, we provide a list of identified use cases of 3D city models (with a description of each), and their applications. Our study demonstrates that 3D city models are employed in at least 29 use cases that are a part of more than 100 applications. The classified inventory could be useful for scientists as well as stakeholders in the geospatial industry, such as companies and national mapping agencies, as it may serve as a reference document to better position their operations, design product portfolios, and to better understand the market.

/pdf/applications-of-3d-city-models-state-of-the-art-review-3yewcl5e4i.pdf

Applications of 3D City Models: State of the Art Review

WiFi localization, the task of determining the physical location of a mobile device from wireless signal strengths, has been shown to be an accurate method of indoor and outdoor localization and a powerful building block for location-aware applications. However, most localization techniques require a training set of signal strength readings labeled against a ground truth location map, which is prohibitive to collect and maintain as maps grow large. In this paper we propose a novel technique for solving the WiFi SLAM problem using the Gaussian Process Latent Variable Model (GPLVM) to determine the latent-space locations of unlabeled signal strength data. We show how GPLVM, in combination with an appropriate motion dynamics model, can be used to reconstruct a topological connectivity graph from a signal strength sequence which, in combination with the learned Gaussian Process signal strength model, can be used to perform efficient localization.

WiFi-SLAM Using G aussian Process Latent Variable Models

Integrity is one criteria to evaluate GNSS performance, which was first introduced in the aviation field. It is a measure of trust which can be placed in the correctness of the information supplied by the total system. In recent years, many GNSS-based applications emerge in the urban environment including liability critical ones, so the concept of integrity attracts more and more attention from urban GNSS users. However, the algorithms developed for the aerospace domain cannot be introduced directly to the GNSS land applications. This is because a high data redundancy exists in the aviation domain and the hypothesis that only one failure occurs at a time is made, which is not the case for the urban users. The main objective of this paper is to provide an overview of the past and current literature discussing the GNSS integrity for urban transport applications so as to point out possible challenges faced by GNSS receivers in such scenario. Key differences between integrity monitoring scheme in aviation domain and urban transport field are addressed. And this paper also points out several open research issues in this field.

/pdf/gnss-position-integrity-in-urban-environments-a-review-of-1ved0w5512.pdf

GNSS Position Integrity in Urban Environments: A Review of Literature

Indoor location based services challenges, requirements and usability of current solutions

Positioning using the Global Positioning System (GPS) is unreliable in dense urban areas with tall buildings and/or narrow streets, known as ‘urban canyons’. This is because the buildings block, reflect or diffract the signals from many of the satellites. This paper investigates the use of 3-Dimensional (3-D) building models to predict satellite visibility. To predict Global Navigation Satellite System (GNSS) performance using 3-D building models, a simulation has been developed. A few optimized methods to improve the efficiency of the simulation for real-time purposes were implemented. Diffraction effects of satellite signals were considered to improve accuracy. The simulation is validated using real-world GPS and GLObal NAvigation Satellite System (GLONASS) observations.

The performance of current and future GNSS in urban canyons is then assessed by simulation using an architectural city model of London with decimetre-level accuracy. GNSS availability, integrity and precision is evaluated over pedestrian and vehicle routes within city canyons using different combinations of GNSS constellations. The results show that using GPS and GLONASS together cannot guarantee 24-hour reliable positioning in urban canyons. However, with the addition of Galileo and Compass, currently under construction, reliable GNSS performance can be obtained at most, but not all, of the locations in the test scenarios. The modelling also demonstrates that GNSS availability is poorer for pedestrians than for vehicles and verifies that cross-street positioning errors are typically larger than along-street due to the geometrical constraints imposed by the buildings. For many applications, this modelling technique could also be used to predict the best route through a city at a given time, or the best time to perform GNSS positioning at a given location.

/pdf/multi-constellation-gnss-performance-evaluation-for-urban-4wz28j1fn1.pdf

Multi-Constellation GNSS Performance Evaluation for Urban Canyons Using Large Virtual Reality City Models

Global Navigation Satellite System (GNSS) shadow matching is a new positioning technique that determines position by comparing the measured signal availability and strength with predictions made using a three-dimensional (3D) city model. It complements conventional GNSS positioning and can significantly improve cross-street positioning accuracy in dense urban environments. This paper describes how shadow matching has been adapted to work on an Android smartphone and presents the first comprehensive performance assessment of smartphone GNSS shadow matching. Using GPS and GLONASS data recorded at 20 locations within central London, it is shown that shadow matching significantly outperforms conventional GNSS positioning in the cross-street direction. The success rate for obtaining a cross-street position accuracy within 5 m, enabling the correct side of a street to be determined, was 54·50% using shadow matching, compared to 24·77% for the conventional GNSS position. The likely performance of four-constellation shadow matching is predicted, the feasibility of a large-scale implementation of shadow matching is assessed, and some methods for improving performance are proposed. A further contribution is a signal-to-noise ratio analysis of the direct line-of-sight and non-line-of-sight signals received on a smartphone in a dense urban environment.

/pdf/smartphone-shadow-matching-for-better-cross-street-gnss-1n17f6kv7d.pdf

Smartphone Shadow Matching for Better Cross-street GNSS Positioning in Urban Environments

Global navigation satellite system (GNSS) positioning is widely used in land vehicle and pedestrian navigation systems. Nevertheless, in urban canyons GNSS remains inaccurate due to building blockages and reflections, especially in the cross-street direction. Shadow matching is a new technique, recently proposed for improving the cross-street positioning accuracy using a 3D model of the nearby buildings. This paper presents a number of advances in the shadow-matching algorithm. First, a positioning algorithm has been developed, interpolating between the top-scoring candidate positions. Furthermore, a new scoring scheme has been developed that accounts for signal diffraction and reflection. Finally, the efficiency of the process used to generate the grid of building boundaries used for predicting satellite visibility has been improved. Real-world GNSS data has been collected at 22 different locations in central London to provide the first comprehensive and statistical performance analysis of shadow matching. © 2013 Institute of Navigation.

GNSS Shadow Matching: Improving Urban Positioning Accuracy Using a 3D City Model with Optimized Visibility Scoring Scheme

Reliable metres-level positioning in dense urban areas is difficult to achieve cost-effectively using a single method The way forward is to combine multiple positioning techniques This paper introduces the concept of intelligent urban positioning (IUP), which combines ? Multi-constellation GNSS; ? Multiple techniques for detecting non-line-of-sight (NLOS) signal propagation; and ? Multiple techniques using three-dimensional mapping IUP may also be extended to incorporate other position-fixing and dead-reckoning sensors The paper begins by explaining the limitations of conventional GNSS positioning in dense urban environments It then introduces the potential ingredients of intelligent urban positioning, a mixture of new and established techniques, and discusses how they might be combined 3D mapping may be used for conventional map matching, height aiding, NLOS signal detection, reflection prediction and shadow matching, a new method for determining position by comparing measured and predicted satellite visibility NLOS reception may also be detected using consistency checking, C/N0 measurement, dual-polarization antenna technology, an antenna array and a sky-pointing camera The results of a preliminary demonstration of the IUP concept using GPS and GLONASS data collected in London are then presented In this test, conventional GNSS positioning, aided by consistency-based LOS detection is combined with shadow matching In the example presented, a horizontal position error of less than 2m was obtained, compared to about 25m for conventional GNSS positioning This clearly demonstrates the potential of the IUP approach Note, however, that further research is needed to improve the reliability

Intelligent Urban Positioning using Multi-Constellation GNSS with 3D Mapping and NLOS Signal Detection

In the past few decades, global navigation satellite system (GNSS) technology has been widely used in structural health monitoring (SHM), and the monitoring mode has evolved from long-term deformation monitoring to dynamic monitoring. This paper gives an overview of GNSS-based dynamic monitoring technologies for SHM. The review is classified into three parts, which include GNSS-based dynamic monitoring technologies for SHM, the improvement of GNSS-based dynamic monitoring technologies for SHM, as well as denoising and detrending algorithms. The significance and progress of Real-Time Kinematic (RTK), Precise Point Position (PPP), and direct displacement measurement techniques, as well as single-frequency technology for dynamic monitoring, are summarized, and the comparison of these technologies is given. The improvement of GNSS-based dynamic monitoring technologies for SHM is given from the perspective of multi-GNSS, a high-rate GNSS receiver, and the integration between the GNSS and accelerometer. In addition, the denoising and detrending algorithms for GNSS-based observations for SHM and corresponding applications are summarized. Challenges of low-cost and widely covered GNSS-based technologies for SHM are discussed, and problems are posed for future research.

https://www.mdpi.com/2072-4292/11/9/1001/pdf

Lei Wang

Papers

Multi-Constellation GNSS Performance Evaluation for Urban Canyons Using Large Virtual Reality City Models

Smartphone Shadow Matching for Better Cross-street GNSS Positioning in Urban Environments

GNSS Shadow Matching: Improving Urban Positioning Accuracy Using a 3D City Model with Optimized Visibility Scoring Scheme

Intelligent Urban Positioning using Multi-Constellation GNSS with 3D Mapping and NLOS Signal Detection

A Review of Global Navigation Satellite System (GNSS)-Based Dynamic Monitoring Technologies for Structural Health Monitoring